René's URL Explorer Experiment


Title: Task evals • RUNME

Open Graph Title: Task evals • RUNME

Description: runme eval is experimental. The command group is intended for agent task eval workflows and may change as the eval workflow matures.

Open Graph Description: runme eval is experimental. The command group is intended for agent task eval workflows and may change as the eval workflow matures.

Keywords:

Opengraph URL: https://runme.dev

X: @statefulhq

Generator: Docusaurus v3.10.1

direct link

Domain: docs.runme.dev


Hey, it has json ld scripts:
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Agent task evals (experimental)","item":"https://docs.runme.dev/eval/"}]}

og:localeen
docusaurus_localeen
docsearch:languageen
Nonetext/html; charset=utf-8
languageEnglish
authorStateful Inc.
contactcontact@stateful.com
twitter:cardsummary_large_image
og:site_nameRunme.dev
og:typewebsite
docusaurus_versioncurrent
docusaurus_tagdocs-default-current
docsearch:versioncurrent
docsearch:docusaurus_tagdocs-default-current

Links:

Skip to main contenthttps://docs.runme.dev/eval#__docusaurus_skipToContent_fallback
New post: Sure, Your Claude Is Doing Amazing Things. Prove It. →https://runme.dev/blog/runme-eval
https://docs.runme.dev/
Documentationhttps://docs.runme.dev/
Communityhttps://runme.dev/community
Bloghttps://runme.dev/blog
Open Sourcehttps://github.com/runmedev/runme
▶ Welcomehttps://docs.runme.dev/
GitOps Workflowhttps://docs.runme.dev/workflow
Installationhttps://docs.runme.dev/installation/
Getting Startedhttps://docs.runme.dev/getting-started/
Usagehttps://docs.runme.dev/usage/
Configurationhttps://docs.runme.dev/configuration/
Guideshttps://docs.runme.dev/guide/
Resourceshttps://docs.runme.dev/resources/
Agent task evals (experimental)https://docs.runme.dev/eval/
Quickstarthttps://docs.runme.dev/eval/quickstart
Command referencehttps://docs.runme.dev/eval/reference
https://docs.runme.dev/
Harbor's task, dataset, trial, and job modelhttps://www.harborframework.com/docs
https://docs.runme.dev/eval#why-use-runme-eval
https://docs.runme.dev/eval#workdir-staging
https://docs.runme.dev/eval#git-backed-promotion
https://docs.runme.dev/eval#prerequisites
open a GitHub issuehttp://github.com/runmedev/runme/issues/new
https://docs.runme.dev/eval#defaults
https://docs.runme.dev/eval#commands
Quickstarthttps://docs.runme.dev/eval/quickstart
Command referencehttps://docs.runme.dev/eval/reference
Edit this pagehttps://github.com/runmedev/docs.runme.dev/edit/main/docs/eval/index.md
PreviousSecurityhttps://docs.runme.dev/resources/security
NextQuickstarthttps://docs.runme.dev/eval/quickstart
Why use runme eval?https://docs.runme.dev/eval#why-use-runme-eval
Workdir staginghttps://docs.runme.dev/eval#workdir-staging
Git-backed promotionhttps://docs.runme.dev/eval#git-backed-promotion
Prerequisiteshttps://docs.runme.dev/eval#prerequisites
Defaultshttps://docs.runme.dev/eval#defaults
Commandshttps://docs.runme.dev/eval#commands

Viewport: width=device-width,initial-scale=1

Robots: index, follow


URLs of crawlers that visited me.